Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5244 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.6609. Min Act: -0.0000

Data Index: 1598614 (Python Code)

Max Activating Token Index: 848

Text #1

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.7512. Min Act: -0.0000

Data Index: 1480118 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1566450 (Python Code)

Max Activating Token Index: 738

Text #3

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1648006 (Python Code)

Max Activating Token Index: 496

Text #4

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.3841. Min Act: -0.0000

Data Index: 1593951 (Python Code)

Max Activating Token Index: 615

Text #5

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.3395. Min Act: -0.0000

Data Index: 1594753 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1361043 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.3165. Min Act: -0.0000

Data Index: 1508637 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1429224 (Python Code)

Max Activating Token Index: 796

Text #9

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.2784. Min Act: -0.0000

Data Index: 1486717 (Python Code)

Max Activating Token Index: 884

Text #10

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1414211 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.2891. Min Act: -0.0000

Data Index: 1587698 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1655617 (Python Code)

Max Activating Token Index: 901

Text #13

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.2535. Min Act: -0.0000

Data Index: 1556872 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1371207 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1640008 (Python Code)

Max Activating Token Index: 787

Text #16

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1397745 (Python Code)

Max Activating Token Index: 745

Text #17

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.2741. Min Act: -0.0000

Data Index: 1427380 (Python Code)

Max Activating Token Index: 919

Text #18

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1361851 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1638529 (Python Code)

Max Activating Token Index: 757